INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     konflikt
    0.43
     boycot
    0.41
     distrust
    0.41
     persuaded
    0.41
     bureaucratic
    0.40
     ayahuasca
    0.40
     denkt
    0.40
     bureaucr
    0.40
     स्मरण
    0.39
     fraud
    0.39
    POSITIVE LOGITS
     spill
    0.78
     spilled
    0.74
     splash
    0.73
     strewn
    0.72
     spills
    0.71
     splashed
    0.71
     messy
    0.69
     splatter
    0.67
     spilling
    0.65
     splashing
    0.64
    Act Density 0.090%

    No Known Activations